Multi-view Dense Depth Map Estimation through Match Propagation
-
摘要: 提出一种高精度的基于匹配扩散的稠密深度图估计算法. 算法分为像素级与区域级两阶段的匹配扩散过程.前者主要对视图间的稀疏特征点匹配进行扩散以获取相对稠密的初始深度图; 而后者则在多幅初始深度图的基础上, 根据场景分段平滑的假设, 在能量函数最小化框架下利用平面拟合及多方向平面扫描等方法解决存在匹配多义性问题区域(如弱纹理区域)的深度推断问题. 在标准数据集及真实数据集上的实验表明, 本文算法对视图中的光照变化、透视畸变等因素具有较强的适应性, 并能有效地对弱纹理区域的深度信息进行推断, 从而可以获得高精度、稠密的深度图.Abstract: The paper proposes a highly accurate multi-view dense depth map estimation algorithm through match propagation. The algorithm is composed of two match propagation processes: a pixel-level propagation process and a region-level propagation process. The former mainly propagates sparse feature matches between views to obtain an initial depth map, the latter, based on multiple initial depth maps and piecewise planar scene assumption, tackles the matching ambiguity problem of some regions (e.g. low texture region) by adopting plane fitting and multiple direction plane sweeping within the framework of minimizing some special energy function. Experiments on standard data set and real-world data set show that our proposed algorithm not only has better adaptability to many factors, e.g. perspective distortion and illumination variance, but also can effectively resolve the depth estimation problem of low texture regions and obtain more accurate and dense depth maps.
-
Key words:
- Low texture /
- match propagation /
- plane sweeping /
- energy function /
- depth map
-
[1] Shen S. Accurate multiple view 3D reconstruction using patch-based stereo for large-scale scenes. IEEE Transactions on Image Processing, 2013, 22(3): 1901-1914 [2] Tola E, Strecha C, Fua P. Efficient large-scale multi-view stereo for ultra high-resolution image sets. Machine Vision and Applications, 2012, 23(5): 903-920 [3] Wang L, Yang R G. Global stereo matching leveraged by sparse ground control points. In: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI: IEEE, 2011. 3033-3040 [4] Juho K, Brandt S S. Quasi-dense wide baseline matching using match propagation. In: Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN: IEEE, 2007. 1-8 [5] Koskenkorva P, Kannala J, Brandt S S. Quasi-dense wide baseline matching for three views. In: Proceedings of the 2010 IEEE Conference on Pattern Recognition. Istanbul, Turkey: IEEE, 2010. 806-809 [6] Taguchi Y, Wilburn B, Zitnick C L. Stereo reconstruction with mixed pixels using adaptive over-segmentation. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK: IEEE, 2008. 1-8 [7] Wang Z F, Zheng Z G. A region based stereo matching algorithm using cooperative optimization. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK: IEEE, 2008. 1-8 [8] Bleyer M, Gelautz M. A layered stereo matching algorithm using image segmentation and global visibility constraints. ISPRS Journal of Photogrammetry and Remote Sensing, 2005, 59(3): 128-150 [9] Wang D L, Lim K B. Obtaining depth map from segment-based stereo matching using graph cuts. Journal of Visual Communication and Image Representation, 2011, 22(4): 325-331 [10] Klaus A, Sormann M, Karner K. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In: Proceedings of the 2006 IEEE Conference on Pattern Recognition. Hong Kong, China: IEEE, 2006. 15-18 [11] Zhang G F, Jia J Y, Wong T T, Bao H J. Consistent depth maps recovery from a video sequence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(6): 974-988 [12] Lhuillier M, Quan L. A quasi-dense approach to surface reconstruction from uncalibrated images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 418-433 [13] Xu Zhen-Hui, Zhang Feng, Sun Feng-Mei, Hu Zhan-Yi. Quasi-dense matching by neighborhood transfer for fish-eye images. Acta Automatica Sinica, 2009, 35(9): 1159-1167(许振辉, 张峰, 孙凤梅, 胡占义. 基于邻域传递的鱼眼图像的准稠密匹配. 自动化学报, 2009, 35(9): 1159-1167) [14] Tao H, Sawhney H S, Kumar R. A global matching framework for stereo computation. In: Proceedings of the 8th International Conference on Computer Vision. Vancouver, Canada: IEEE, 2001. 532-539 [15] Wei Y, Quan L. Region-based progressive stereo matching. In: Proceedings of the 2004 IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2004. I-106-I-113 [16] Gallup D, Frahm J M, Pollefeys M. Piecewise planar and non-planar stereo for urban scene reconstruction. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA: IEEE, 2010. 1418-1425 [17] Furukawa Y, Curless B, Seitz S M, Szeliski R. Manhattan-world stereo. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA: IEEE, 2009. 1422-1429 [18] Mičušík B, Košecká J. Multi-view superpixel stereo in urban environments. International Journal of Computer Vision, 2010, 89(1): 106-119 [19] Mikolajczyk K, Schmid C. Scale & affine invariant interest point detectors. International Journal of Computer Vision, 2004, 60(1): 63-86 [20] Strecha C, von Hansen W, Van Gool L, Fua P, Thoennessen U. On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK: IEEE, 2008. 1-8 [21] Morel J M, Yu G S. ASIFT: a new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences, 2009, 2(2): 438-469 [22] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [23] Xiao J H, Shah M. Two-frame wide baseline matching. In: Proceedings of the 9th International Conference on Computer Vision. Nice, France: IEEE, 2003. 603-609 [24] Deng Bao-Song, Song Han-Chen, Yang Bing, Wu Ling-Da. Feature point matching based on affine iterative model. Journal of Image and Graphics, 2007, 12(4): 678-683(邓宝松, 宋汉辰, 杨冰, 吴玲达. 基于仿射迭代模型的特征点匹配算法. 中国图象图形学报, 2007, 12(4): 678-683) [25] Steele K L, Egbert P K. Correspondence expansion for wide baseline stereo. In: Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE, 2005. 1055-1062 [26] Hartley R, Zisserman A. Multiple View Geometry in Computer Vision. Cambridge: Cambridge University Press, 2004. 1-672 [27] Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619 [28] Campbell N D F, Vogiatzis G, Hernández C, Cipolla R. Using multiple hypotheses to improve depth-maps for multi-view stereo. In: Proceedings of the 10th European Conference on Computer Vision. Marseille, France: Springer, 2008. 766-779 [29] Zhang Y H, Hartley R, Mashford J, Burn S. Superpixels, occlusion and stereo. In: Proceedings of the 2011 IEEE Conference on Digital Image Computing Techniques and Applications. Noosa, Australia: IEEE, 2011. 84-91 [30] Çiğla C, Zabulis X, Alatan A A. Segment-based stereo-matching via plane and angle sweeping. In: Proceedings of the 2007 IEEE Conference on 3DTV. Kos, Greece: IEEE, 2007. 1-4 [31] Gallup D, Frahm J M, Mordohai P, Yang Q X. Real-time plane-sweeping stereo with multiple sweeping directions. In: Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA: IEEE, 2007. 1-8 [32] Tola E, Lepetit V, Fua P. Daisy: an efficient dense descriptor applied to wide-baseline stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 815-830 [33] Furukawa Y, Ponce J. Accurate, dense, and robust multiview stereopsis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(8): 1362-1376
点击查看大图
计量
- 文章访问数: 1796
- HTML全文浏览量: 64
- PDF下载量: 1246
- 被引次数: 0